© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 30717
    Prev
    Next
    INDEX
    Explanations

    actions related to digital interaction or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iland
    -0.07
    ään
    -0.07
    orie
    -0.07
    bris
    -0.06
    weit
    -0.06
    Äįka
    -0.06
     Raum
    -0.06
     Beled
    -0.06
    ÃŃnÄĽ
    -0.06
    ansa
    -0.06
    POSITIVE LOGITS
    mere
    0.11
     simply
    0.10
     simplement
    0.10
     merely
    0.08
     mere
    0.07
     suddenly
    0.07
     einfach
    0.07
     Simply
    0.07
     пÑĢоÑģÑĤо
    0.07
    Simply
    0.07
    Activations Density 0.025%

    No Known Activations